The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
- URL: http://arxiv.org/abs/2404.14581v1
- Date: Mon, 22 Apr 2024 21:00:13 GMT
- Title: The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
- Authors: Yuying Li, Zeyan Liu, Junyi Zhao, Liangqin Ren, Fengjun Li, Jiebo Luo, Bo Luo,
- Abstract summary: We present a systematic attempt at understanding and detecting AI-generated images (AI-art) in adversarial scenarios.
The dataset, named ARIA, contains over 140K images in five categories: artworks (painting), social media images, news photos, disaster scenes, and anime pictures.
- Score: 47.08666835021915
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Generative AI models can produce high-quality images based on text prompts. The generated images often appear indistinguishable from images generated by conventional optical photography devices or created by human artists (i.e., real images). While the outstanding performance of such generative models is generally well received, security concerns arise. For instance, such image generators could be used to facilitate fraud or scam schemes, generate and spread misinformation, or produce fabricated artworks. In this paper, we present a systematic attempt at understanding and detecting AI-generated images (AI-art) in adversarial scenarios. First, we collect and share a dataset of real images and their corresponding artificial counterparts generated by four popular AI image generators. The dataset, named ARIA, contains over 140K images in five categories: artworks (painting), social media images, news photos, disaster scenes, and anime pictures. This dataset can be used as a foundation to support future research on adversarial AI-art. Next, we present a user study that employs the ARIA dataset to evaluate if real-world users can distinguish with or without reference images. In a benchmarking study, we further evaluate if state-of-the-art open-source and commercial AI image detectors can effectively identify the images in the ARIA dataset. Finally, we present a ResNet-50 classifier and evaluate its accuracy and transferability on the ARIA dataset.
Related papers
- ANID: How Far Are We? Evaluating the Discrepancies Between AI-synthesized Images and Natural Images through Multimodal Guidance [19.760989919485894]
We introduce an AI-Natural Image Discrepancy Evaluation benchmark aimed at addressing the critical question: textithow far are AI-generated images from truly realistic images?
We have constructed a large-scale multimodal dataset, the Distinguishing Natural and AI-generated Images (DNAI) dataset, which includes over 440,000 AIGI samples generated by 8 representative models.
Our fine-grained assessment framework provides a comprehensive evaluation of the DNAI dataset across five key dimensions.
arXiv Detail & Related papers (2024-12-23T15:08:08Z) - Human vs. AI: A Novel Benchmark and a Comparative Study on the Detection of Generated Images and the Impact of Prompts [5.222694057785324]
This work examines the influence of the prompt's level of detail on the detectability of fake images.
We create a novel dataset, COCOXGEN, which consists of real photos from the COCO dataset as well as images generated with SDXL and Fooocus.
Our user study with 200 participants shows that images generated with longer, more detailed prompts are detected significantly more easily than those generated with short prompts.
arXiv Detail & Related papers (2024-12-12T20:37:52Z) - Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors [62.63467652611788]
We introduce SEMI-TRUTHS, featuring 27,600 real images, 223,400 masks, and 1,472,700 AI-augmented images.
Each augmented image is accompanied by metadata for standardized and targeted evaluation of detector robustness.
Our findings suggest that state-of-the-art detectors exhibit varying sensitivities to the types and degrees of perturbations, data distributions, and augmentation methods used.
arXiv Detail & Related papers (2024-11-12T01:17:27Z) - KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities [93.74881034001312]
We conduct a systematic study on the fidelity of entities in text-to-image generation models.
We focus on their ability to generate a wide range of real-world visual entities, such as landmark buildings, aircraft, plants, and animals.
Our findings reveal that even the most advanced text-to-image models often fail to generate entities with accurate visual details.
arXiv Detail & Related papers (2024-10-15T17:50:37Z) - Zero-Shot Detection of AI-Generated Images [54.01282123570917]
We propose a zero-shot entropy-based detector (ZED) to detect AI-generated images.
Inspired by recent works on machine-generated text detection, our idea is to measure how surprising the image under analysis is compared to a model of real images.
ZED achieves an average improvement of more than 3% over the SoTA in terms of accuracy.
arXiv Detail & Related papers (2024-09-24T08:46:13Z) - A Sanity Check for AI-generated Image Detection [49.08585395873425]
We propose AIDE (AI-generated Image DEtector with Hybrid Features) to detect AI-generated images.
AIDE achieves +3.5% and +4.6% improvements to state-of-the-art methods.
arXiv Detail & Related papers (2024-06-27T17:59:49Z) - ASAP: Interpretable Analysis and Summarization of AI-generated Image Patterns at Scale [20.12991230544801]
Generative image models have emerged as a promising technology to produce realistic images.
There is growing demand to empower users to effectively discern and comprehend patterns of AI-generated images.
We develop ASAP, an interactive visualization system that automatically extracts distinct patterns of AI-generated images.
arXiv Detail & Related papers (2024-04-03T18:20:41Z) - Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images [67.18010640829682]
We show that AI-generated images introduce an invisible relevance bias to text-image retrieval models.
The inclusion of AI-generated images in the training data of the retrieval models exacerbates the invisible relevance bias.
We propose an effective training method aimed at alleviating the invisible relevance bias.
arXiv Detail & Related papers (2023-11-23T16:22:58Z) - Online Detection of AI-Generated Images [17.30253784649635]
We study generalization in this setting, training on N models and testing on the next (N+k)
We extend this approach to pixel prediction, demonstrating strong performance using automatically-generated inpainted data.
In addition, for settings where commercial models are not publicly available for automatic data generation, we evaluate if pixel detectors can be trained solely on whole synthetic images.
arXiv Detail & Related papers (2023-10-23T17:53:14Z) - CIFAKE: Image Classification and Explainable Identification of
AI-Generated Synthetic Images [7.868449549351487]
This article proposes to enhance our ability to recognise AI-generated images through computer vision.
The two sets of data present as a binary classification problem with regard to whether the photograph is real or generated by AI.
This study proposes the use of a Convolutional Neural Network (CNN) to classify the images into two categories; Real or Fake.
arXiv Detail & Related papers (2023-03-24T16:33:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.